
# Import required libraries and dependencies
import pandas as pd
import hvplot.pandas
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler


# Load the data into a Pandas DataFrame
df_market_data = pd.read_csv(
    "Resources/crypto_market_data.csv",
    index_col="coin_id")

# Display sample data
df_market_data.head(40)


# Generate summary statistics
df_market_data.describe()


# Plot your data to see what's in your DataFrame
df_market_data.hvplot.line(
    width=800,
    height=400,
    rot=90
)


# Use the `StandardScaler()` module from scikit-learn to normalize the data from the CSV file

df_market_data_scaled = StandardScaler().fit_transform(df_market_data[['price_change_percentage_24h','price_change_percentage_7d','price_change_percentage_14d','price_change_percentage_30d','price_change_percentage_60d','price_change_percentage_200d','price_change_percentage_1y']])
# Create a DataFrame with the scaled data
df_market_data_scaled = pd.DataFrame(df_market_data_scaled,columns=['price_change_percentage_24h','price_change_percentage_7d','price_change_percentage_14d','price_change_percentage_30d','price_change_percentage_60d','price_change_percentage_200d','price_change_percentage_1y'])


# Copy the crypto names from the original data
crypto_name_index = df_market_data.index

# Set the coinid column as index
df_market_data_scaled.index = crypto_name_index

# Display sample data
df_market_data_scaled


crypto_name_index

Index(['bitcoin', 'ethereum', 'tether', 'ripple', 'bitcoin-cash',
       'binancecoin', 'chainlink', 'cardano', 'litecoin', 'bitcoin-cash-sv',
       'crypto-com-chain', 'usd-coin', 'eos', 'monero', 'tron', 'tezos', 'okb',
       'stellar', 'cosmos', 'cdai', 'neo', 'wrapped-bitcoin', 'leo-token',
       'huobi-token', 'nem', 'binance-usd', 'iota', 'vechain', 'zcash',
       'theta-token', 'dash', 'ethereum-classic', 'ethlend', 'maker', 'havven',
       'omisego', 'celsius-degree-token', 'ontology', 'ftx-token', 'true-usd',
       'digibyte'],
      dtype='object', name='coin_id')


# Create a list with the number of k-values from 1 to 11

k = list(range(1,11))
k

[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]


# Create an empty list to store the inertia values

inertia =[]
# Create a for loop to compute the inertia with each possible value of k
for i in k:
    k_model = KMeans(n_clusters = i,random_state=  1)
    k_model.fit(df_market_data_scaled)
    inertia.append(k_model.inertia_)
# Inside the loop:
# 1. Create a KMeans model using the loop counter for the n_clusters
# 2. Fit the model to the data using `df_market_data_scaled`
# 3. Append the model.inertia_ to the inertia list

C:\Users\samit\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:1036: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.
  warnings.warn(


# Create a dictionary with the data to plot the Elbow curve
elbow_data = {"K": k,"Inertia": inertia}
df_elbow_scaled = pd.DataFrame(elbow_data)

# Create a DataFrame with the data to plot the Elbow curve
df_elbow_scaled.head()


# Plot a line chart with all the inertia values computed with 
elbow_plot_orginal = df_elbow_scaled.hvplot.line(
    x="K", 
    y="Inertia", 
    title="Elbow Curve", 
    xticks=k)
df_elbow_scaled.hvplot.line(
    x="K", 
    y="Inertia", 
    title="Elbow Curve", 
    xticks=k)
# the different values of k to visually identify the optimal value for k.


# Initialize the K-Means model using the best value for k
model = KMeans(n_clusters= 4,random_state=1)


# Fit the K-Means model using the scaled data
model.fit(df_market_data_scaled)

KMeans(n_clusters=4, random_state=1)


# Predict the clusters to group the cryptocurrencies using the scaled data
k_lower = model.predict(df_market_data_scaled)

# Print the resulting array of cluster values.
k_lower

array([3, 3, 1, 1, 3, 3, 3, 3, 3, 1, 1, 1, 1, 3, 1, 3, 1, 1, 3, 1, 1, 3,
       1, 1, 1, 1, 1, 1, 3, 1, 1, 1, 0, 3, 1, 1, 2, 1, 1, 1, 1])


# Create a copy of the DataFrame
df_market_data_scaled_prediction = df_market_data_scaled.copy()


# Add a new column to the DataFrame with the predicted clusters
df_market_data_scaled_prediction['cluster_lower']=k_lower

# Display sample data
df_market_data_scaled_prediction.head()


# Create a scatter plot using hvPlot by setting 
# `x="price_change_percentage_24h"` and `y="price_change_percentage_7d"`. 
# Color the graph points with the labels found using K-Means and 
# add the crypto name in the `hover_cols` parameter to identify 
# the cryptocurrency represented by each data point.
cluster_plot_original =  df_market_data_scaled_prediction.hvplot.scatter(
    x="price_change_percentage_24h",
    y="price_change_percentage_7d",
    by="cluster_lower",
    hover_cols ="coin_id"
    ).opts(yformatter = "%.0f")

df_market_data_scaled_prediction.hvplot.scatter(
    x="price_change_percentage_24h",
    y="price_change_percentage_7d",
    by="cluster_lower",
    hover_cols ="coin_id"
    ).opts(yformatter = "%.0f")


# Create a PCA model instance and set `n_components=3`.

pca = PCA(n_components=3)


# Use the PCA model with `fit_transform` to reduce to 
# three principal components.
market_data_pca = pca.fit_transform(df_market_data_scaled)
# View the first five rows of the DataFrame. 
market_data_pca[:5]

array([[-0.60066733,  0.84276006,  0.46159457],
       [-0.45826071,  0.45846566,  0.95287678],
       [-0.43306981, -0.16812638, -0.64175193],
       [-0.47183495, -0.22266008, -0.47905316],
       [-1.15779997,  2.04120919,  1.85971527]])


# Retrieve the explained variance to determine how much information 
# can be attributed to each principal component.
pca.explained_variance_ratio_

array([0.3719856 , 0.34700813, 0.17603793])


# Create a new DataFrame with the PCA data.
df_market_data_pca = pd.DataFrame(market_data_pca,columns = ['PCA1','PCA2','PCA3'])

# Creating a DataFrame with the PCA data

# Copy the crypto names from the original data
df_market_data_pca.index = crypto_name_index

# Set the coinid column as index


# Display sample data
df_market_data_pca


# Create a list with the number of k-values from 1 to 11
k = list(range(1,11))


# Create an empty list to store the inertia values
inertia=[]

# Create a for loop to compute the inertia with each possible value of k

for i in k:
    k_model = KMeans(n_clusters=i,random_state=1)
    k_model.fit(df_market_data_pca)
    inertia.append(k_model.inertia_)
# Inside the loop:
# 1. Create a KMeans model using the loop counter for the n_clusters
# 2. Fit the model to the data using `df_market_data_pca`
# 3. Append the model.inertia_ to the inertia list

C:\Users\samit\anaconda3\lib\site-packages\sklearn\cluster\_kmeans.py:1036: UserWarning: KMeans is known to have a memory leak on Windows with MKL, when there are less chunks than available threads. You can avoid it by setting the environment variable OMP_NUM_THREADS=1.
  warnings.warn(


# Create a dictionary with the data to plot the Elbow curve
elbow_data = {"k":k,"inertia":inertia}
df_elbow = pd.DataFrame(elbow_data)
# Create a DataFrame with the data to plot the Elbow curve
df_elbow.head()


# Plot a line chart with all the inertia values computed with 
# the different values of k to visually identify the optimal value for k.
elbow_pca = df_elbow.hvplot.line(
    x="k", 
    y="inertia", 
    title="Elbow Curve", 
    xticks=k
)
df_elbow.hvplot.line(
    x="k", 
    y="inertia", 
    title="Elbow Curve", 
    xticks=k
)


# Initialize the K-Means model using the best value for k
mdoel = KMeans(n_clusters=4,random_state=1)


# Fit the K-Means model using the PCA data
model.fit(df_market_data_pca)

KMeans(n_clusters=4, random_state=1)


# Predict the clusters to group the cryptocurrencies using the PCA data
k_3 = model.predict(df_market_data_pca)
# Print the resulting array of cluster values.
k_3

array([1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0, 1,
       0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 2, 1, 0, 0, 3, 0, 0, 0, 0])


# Create a copy of the DataFrame with the PCA data
df_market_data_pca_predict = df_market_data_pca.copy()

# Add a new column to the DataFrame with the predicted clusters
df_market_data_pca_predict['market_segment'] = k_3

# Display sample data
df_market_data_pca_predict


# Create a scatter plot using hvPlot by setting 
# `x="PC1"` and `y="PC2"`. 
# Color the graph points with the labels found using K-Means and 
# add the crypto name in the `hover_cols` parameter to identify 
# the cryptocurrency represented by each data point.
cluster_pca = df_market_data_pca_predict.hvplot.scatter(
    x="PCA1",
    y="PCA2",
    by="market_segment"
)
df_market_data_pca_predict.hvplot.scatter(
    x="PCA1",
    y="PCA2",
    by="market_segment"
)


# Composite plot to contrast the Elbow curves
composit_elbow = elbow_pca + elbow_plot_orginal
composit_elbow


# Composite plot to contrast the clusters
composit_cluster = cluster_pca + cluster_plot_original
composit_cluster

	price_change_percentage_24h	price_change_percentage_7d	price_change_percentage_14d	price_change_percentage_30d	price_change_percentage_60d	price_change_percentage_200d	price_change_percentage_1y
coin_id
bitcoin	1.08388	7.60278	6.57509	7.67258	-3.25185	83.51840	37.51761
ethereum	0.22392	10.38134	4.80849	0.13169	-12.88890	186.77418	101.96023
tether	-0.21173	0.04935	0.00640	-0.04237	0.28037	-0.00542	0.01954
ripple	-0.37819	-0.60926	2.24984	0.23455	-17.55245	39.53888	-16.60193
bitcoin-cash	2.90585	17.09717	14.75334	15.74903	-13.71793	21.66042	14.49384
binancecoin	2.10423	12.85511	6.80688	0.05865	36.33486	155.61937	69.69195
chainlink	-0.23935	20.69459	9.30098	-11.21747	-43.69522	403.22917	325.13186
cardano	0.00322	13.99302	5.55476	10.10553	-22.84776	264.51418	156.09756
litecoin	-0.06341	6.60221	7.28931	1.21662	-17.23960	27.49919	-12.66408
bitcoin-cash-sv	0.92530	3.29641	-1.86656	2.88926	-24.87434	7.42562	93.73082
crypto-com-chain	0.61209	-5.67151	-8.53948	-17.44782	-16.47600	226.70782	305.05908
usd-coin	-0.17825	-0.11871	-0.00568	-0.16584	0.04271	-0.15691	-0.19205
eos	0.14477	-1.31177	1.13751	-4.63398	-30.16898	18.06111	-17.56753
monero	0.42961	15.78515	18.41097	38.95974	41.72500	169.52147	141.04116
tron	0.07647	4.23886	1.40337	-12.60389	5.52545	132.88436	59.23821
tezos	-0.67316	8.95665	2.32062	-14.12663	-44.82248	43.42842	140.01279
okb	-2.72700	-4.55389	-5.02662	-10.43847	-2.83120	39.95853	141.95791
stellar	-1.00843	2.07149	-1.08217	-8.12933	-30.80369	84.62157	13.80715
cosmos	-0.95103	16.08534	5.51074	4.57813	-7.20130	185.99786	82.43833
cdai	0.21169	0.05820	0.17076	-2.18147	0.65726	-0.39210	-0.28783
neo	0.49302	2.44243	-9.84803	-21.95472	13.51879	158.64773	131.29655
wrapped-bitcoin	1.10231	7.40537	6.55668	7.37557	-3.58772	83.90520	37.53424
leo-token	-0.13192	-1.34886	-7.02859	3.07525	-7.54455	16.40588	21.00263
huobi-token	-0.40818	1.61798	0.45488	-3.25488	-3.40689	42.23704	24.57164
nem	-0.84990	-0.85140	2.64844	-3.65382	82.86094	216.17761	200.71797
binance-usd	-0.10642	0.04726	0.05902	0.01843	0.09383	0.09959	0.13928
iota	0.41996	6.06830	-3.77714	-4.15281	-34.51894	95.02821	-3.98533
vechain	1.28766	-1.76352	-18.15890	-14.16831	-43.62359	269.70264	202.86827
zcash	-0.60897	10.34780	5.79179	7.37007	-20.54216	122.54767	82.88499
theta-token	-4.56089	-6.09456	-6.57354	31.43355	80.03112	882.65105	701.37599
dash	-1.06006	5.09387	0.51708	-7.79140	-26.22460	6.23435	-2.45897
ethereum-classic	-0.45950	3.05209	-1.26669	2.89572	-25.90799	10.39203	11.11094
ethlend	-13.52786	4.21266	-9.80075	-29.99499	2.13917	2227.92782	7852.08970
maker	-0.60285	8.15400	-1.48854	16.71360	-18.61722	82.53544	10.65279
havven	-4.07216	4.33651	-13.29164	-20.84154	-39.42657	622.92465	678.78427
omisego	4.84033	6.82985	-13.21636	-9.11552	79.27505	585.26307	320.69054
celsius-degree-token	2.51323	0.60354	24.23919	140.79570	223.06437	1590.19149	2009.72217
ontology	-1.35845	-1.21399	-10.56222	-34.70548	-32.70004	54.76717	-12.65493
ftx-token	0.83416	7.10438	-0.20629	-10.56394	5.90295	57.48950	168.37251
true-usd	-0.06197	0.16642	0.10974	0.03090	0.25154	-0.08874	0.40617

	price_change_percentage_24h	price_change_percentage_7d	price_change_percentage_14d	price_change_percentage_30d	price_change_percentage_60d	price_change_percentage_200d	price_change_percentage_1y
count	41.000000	41.000000	41.000000	41.000000	41.000000	41.000000	41.000000
mean	-0.269686	4.497147	0.185787	1.545693	-0.094119	236.537432	347.667956
std	2.694793	6.375218	8.376939	26.344218	47.365803	435.225304	1247.842884
min	-13.527860	-6.094560	-18.158900	-34.705480	-44.822480	-0.392100	-17.567530
25%	-0.608970	0.047260	-5.026620	-10.438470	-25.907990	21.660420	0.406170
50%	-0.063410	3.296410	0.109740	-0.042370	-7.544550	83.905200	69.691950
75%	0.612090	7.602780	5.510740	4.578130	0.657260	216.177610	168.372510
max	4.840330	20.694590	24.239190	140.795700	223.064370	2227.927820	7852.089700

	price_change_percentage_24h	price_change_percentage_7d	price_change_percentage_14d	price_change_percentage_30d	price_change_percentage_60d	price_change_percentage_200d	price_change_percentage_1y
coin_id
bitcoin	0.508529	0.493193	0.772200	0.235460	-0.067495	-0.355953	-0.251637
ethereum	0.185446	0.934445	0.558692	-0.054341	-0.273483	-0.115759	-0.199352
tether	0.021774	-0.706337	-0.021680	-0.061030	0.008005	-0.550247	-0.282061
ripple	-0.040764	-0.810928	0.249458	-0.050388	-0.373164	-0.458259	-0.295546
bitcoin-cash	1.193036	2.000959	1.760610	0.545842	-0.291203	-0.499848	-0.270317
binancecoin	0.891871	1.327295	0.800214	-0.057148	0.778653	-0.188232	-0.225533
chainlink	0.011397	2.572251	1.101647	-0.490495	-0.931954	0.387759	-0.018284
cardano	0.102530	1.508001	0.648885	0.328959	-0.486349	0.065080	-0.155428
litecoin	0.077497	0.334297	0.858520	-0.012646	-0.366477	-0.486266	-0.292351
bitcoin-cash-sv	0.448952	-0.190684	-0.248043	0.051634	-0.529666	-0.532961	-0.206029
crypto-com-chain	0.331280	-1.614844	-1.054521	-0.729931	-0.350155	-0.022866	-0.034570
usd-coin	0.034352	-0.733026	-0.023140	-0.065775	0.002925	-0.550599	-0.282232
eos	0.155710	-0.922491	0.115024	-0.237488	-0.642837	-0.508220	-0.296330
monero	0.262723	1.792602	2.202665	1.437842	0.893865	-0.155893	-0.167644
tron	0.130050	-0.041018	0.147155	-0.543776	0.120116	-0.241118	-0.234014
tezos	-0.151583	0.708196	0.258012	-0.602296	-0.956049	-0.449211	-0.168479
okb	-0.923203	-1.437359	-0.629963	-0.460558	-0.058504	-0.457283	-0.166900
stellar	-0.277543	-0.385209	-0.153243	-0.371816	-0.656403	-0.353387	-0.270874
cosmos	-0.255978	1.840274	0.643565	0.116538	-0.151913	-0.117565	-0.215191
cdai	0.180851	-0.704931	-0.001816	-0.143237	0.016060	-0.551146	-0.282310
neo	0.286546	-0.326301	-1.212670	-0.903134	0.290970	-0.181187	-0.175550
wrapped-bitcoin	0.515453	0.461843	0.769975	0.224045	-0.074674	-0.355054	-0.251623
leo-token	0.051758	-0.928381	-0.871918	0.058782	-0.159250	-0.512071	-0.265036
huobi-token	-0.052032	-0.457229	0.032522	-0.184489	-0.070809	-0.451982	-0.262140
nem	-0.217984	-0.849381	0.297632	-0.199820	1.773127	-0.047361	-0.119226
binance-usd	0.061339	-0.706669	-0.015321	-0.058694	0.004017	-0.550003	-0.281963
iota	0.259097	0.249508	-0.478953	-0.218997	-0.735815	-0.329179	-0.285310
vechain	0.585089	-0.994231	-2.217108	-0.603898	-0.930423	0.077149	-0.117482
zcash	-0.127467	0.929119	0.677532	0.223834	-0.437068	-0.265163	-0.214829
theta-token	-1.612188	-1.682027	-0.816921	1.148607	1.712641	1.502992	0.286977
dash	-0.296940	0.094763	0.040040	-0.358830	-0.558527	-0.535732	-0.284071
ethereum-classic	-0.071312	-0.229484	-0.175544	0.051882	-0.551760	-0.526060	-0.273062
ethlend	-4.981042	-0.045178	-1.206956	-1.212126	0.047736	4.632380	6.088625
maker	-0.125168	0.580730	-0.202356	0.582911	-0.395923	-0.358240	-0.273433
havven	-1.428574	-0.025510	-1.628859	-0.860354	-0.840714	0.898815	0.268647
omisego	1.919812	0.370447	-1.619761	-0.409716	1.696480	0.811207	-0.021888
celsius-degree-token	1.045530	-0.618328	2.907054	5.351455	4.769913	3.148875	1.348488
ontology	-0.409044	-0.906963	-1.298986	-1.393153	-0.696937	-0.422835	-0.292344
ftx-token	0.414711	0.414044	-0.047386	-0.465380	0.128185	-0.416502	-0.145469
true-usd	0.078038	-0.687745	-0.009191	-0.058214	0.007388	-0.550441	-0.281747
digibyte	1.217453	-0.607714	-0.907066	0.449939	-0.662530	0.572367	-0.132482

	K	Inertia
0	1	287.000000
1	2	195.820218
2	3	123.190482
3	4	79.022435
4	5	65.405923

	price_change_percentage_24h	price_change_percentage_7d	price_change_percentage_14d	price_change_percentage_30d	price_change_percentage_60d	price_change_percentage_200d	price_change_percentage_1y	cluster_lower
coin_id
bitcoin	0.508529	0.493193	0.772200	0.235460	-0.067495	-0.355953	-0.251637	3
ethereum	0.185446	0.934445	0.558692	-0.054341	-0.273483	-0.115759	-0.199352	3
tether	0.021774	-0.706337	-0.021680	-0.061030	0.008005	-0.550247	-0.282061	1
ripple	-0.040764	-0.810928	0.249458	-0.050388	-0.373164	-0.458259	-0.295546	1
bitcoin-cash	1.193036	2.000959	1.760610	0.545842	-0.291203	-0.499848	-0.270317	3

Prepare the Data¶

Find the Best Value for k Using the Original Data.¶

Answer the following question:¶

Cluster Cryptocurrencies with K-means Using the Original Data¶

Optimize Clusters with Principal Component Analysis.¶

Answer the following question:¶

Find the Best Value for k Using the PCA Data¶

Answer the following questions:¶

Cluster Cryptocurrencies with K-means Using the PCA Data¶

Visualize and Compare the Results¶

Answer the following question:¶

	PCA1	PCA2	PCA3
coin_id
bitcoin	-0.600667	0.842760	0.461595
ethereum	-0.458261	0.458466	0.952877
tether	-0.433070	-0.168126	-0.641752
ripple	-0.471835	-0.222660	-0.479053
bitcoin-cash	-1.157800	2.041209	1.859715
binancecoin	-0.516534	1.388377	0.804071
chainlink	-0.450711	0.517699	2.846143
cardano	-0.345600	0.729439	1.478013
litecoin	-0.649468	0.432165	0.600303
bitcoin-cash-sv	-0.759014	-0.201200	-0.217653
crypto-com-chain	-0.248198	-1.376252	-1.462026
usd-coin	-0.438408	-0.175337	-0.663388
eos	-0.693425	-0.473815	-0.527597
monero	0.060499	2.909404	1.498571
tron	-0.393352	-0.108192	-0.012756
tezos	-0.796176	-0.494409	1.082812
okb	0.064075	-1.269825	-1.098829
stellar	-0.489015	-0.732719	-0.062543
cosmos	-0.306272	0.703415	1.714224
cdai	-0.513528	-0.142802	-0.656566
neo	-0.362120	-0.986914	-0.728752
wrapped-bitcoin	-0.604265	0.827398	0.439316
leo-token	-0.413296	-0.674115	-1.076628
huobi-token	-0.407483	-0.212507	-0.351426
nem	0.608974	0.563532	-1.148742
binance-usd	-0.450211	-0.151019	-0.647401
iota	-0.764665	-0.517886	0.204990
vechain	-0.556315	-1.938209	-1.261776
zcash	-0.425147	0.492976	1.058048
theta-token	2.676868	-0.013954	-1.965207
dash	-0.613923	-0.479337	0.339565
ethereum-classic	-0.579924	-0.356334	-0.114942
ethlend	8.089018	-3.896891	2.301382
maker	-0.389045	0.165041	0.379414
havven	0.865762	-2.261882	0.275583
omisego	0.111675	0.428316	-1.205398
celsius-degree-token	4.792395	6.767679	-1.986985
ontology	-0.632355	-2.108117	-0.652227
ftx-token	-0.593142	0.021485	0.209911
true-usd	-0.458131	-0.135734	-0.635284
digibyte	-0.297910	-0.191126	-0.909602

	k	inertia
0	1	256.874086
1	2	165.901994
2	3	93.774626
3	4	49.665497
4	5	38.352251